Classification of alcoholic EEG using wavelet packet decomposition, principal component analysis, and combination of genetic algorithm and neural network

Alcoholism is a disorder characterized by excessive consumption and dependence on alcohol. There are various ways to detect whether a patient is addicted to alcohol, one of them by brain detection using electroencephalograph (EEG). However, the signals generated by the EEG recorder should be prepare...

Full description

Saved in:
Bibliographic Details
Published in2017 11th International Conference on Information & Communication Technology and System (ICTS) pp. 19 - 24
Main Authors Saddam, Muhammad, Tjandrasa, Handayani, Navastara, Dini Adni
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2017
Subjects
Alcoholic beverages
Alcoholism
Biological neural networks
EEG
Electroencephalography
Genetic Algorithm
Genetic algorithms
Neural Network
Principal component analysis
Wavelet Packet Decomposition
Wavelet packets
Online AccessGet full text

Cover

More Information
Summary:Alcoholism is a disorder characterized by excessive consumption and dependence on alcohol. There are various ways to detect whether a patient is addicted to alcohol, one of them by brain detection using electroencephalograph (EEG). However, the signals generated by the EEG recorder should be prepared to do further processing to detect brain abnormalities automatically. Therefore, this research implements Wavelet Packet Decomposition (WPD) method for feature extraction, Principal Component Analysis (PCA) for dimension reduction, and Back Propagation Neural Network optimized with Genetic Algorithm for alcohol addiction classification. Based on the experiment results, the best performance was 94.00% accuracy with decomposition of 3 levels, taking 30% of the features, and classification using Neural Network and Genetic Algorithm with learning rate of 0.1.
ISBN:9781538628256
1538628252
ISSN:2996-1378
DOI:10.1109/ICTS.2017.8265600